Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection

Domain:

natural language processing

Record type:

paper
Creator:
Do,ColDijKla
Host:avatar
We compare using a PHOIBLE-based phone mapping method and using phonological features input in transfer learning for TTS in low-resource languages. We use diverse source languages (English, Finnish, Hindi, Japanese, and Russian) and target languages (Bulgarian, Georgian, Kazakh, Swahili, Urdu, and Uzbek) to test the language-independence of the methods and enhance the findings' applicability. We use Character Error Rates from automatic speech recognition and predicted Mean Opinion Scores for evaluation. Results show that both phone mapping and features input improve the output quality and the latter performs better, but these effects also depend on the specific language combination. We also compare the recently-proposed Angular Similarity of Phone Frequencies (ASPF) with a family tree-based distance measure as a criterion to select source languages in transfer learning. ASPF proves effective if label-based phone input is used, while the language distance does not have expected effects. Accepted at the Speech Synthesis Workshop 2023

Visit

arxiv.org

Tasks

speech processingtext to speechtransfer learning

Languages

Swahili

Tags

Computation and LanguageAudio and Speech Processing

Similar

Using Transfer Learning to Realize Low Resource Dungan Language Speech SynthesisTypological Features in Source Language Selection for Cross-Lingual NER on Low-Resource African LanguagesThe Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-SpeechComparing Source Language Selection Strategies for Multi-Source Cross-Lingual Transfer to African LanguagesIntermediate-Task Selection Strategies for Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesText-to-speech system for low-resource language using cross-lingual transfer learning and data augmentation

Using Transfer Learning to Realize Low Resource Dungan Language Speech Synthesis

This article presents a transfer-learning-based method to improve the synthesized speech quality of

Typological Features in Source Language Selection for Cross-Lingual NER on Low-Resource African Languages

Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data fr

The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech

We compare phone labels and articulatory features as input for cross-lingual transfer learning in te

Comparing Source Language Selection Strategies for Multi-Source Cross-Lingual Transfer to African Languages

Intermediate-Task Selection Strategies for Zero-Shot Cross-Lingual Transfer in Low-Resource Languages

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before

Text-to-speech system for low-resource language using cross-lingual transfer learning and data augmentation

Abstract Deep learning techniques are currently being applied in automated text-to-speech (TTS) sys